Reinforcement Learning‐Based Adaptive Optimal Containment Control for Constrained Nonlinear Multiagent Systems
An observer‐actor‐critic architecture is introduced, where observers are used to estimate unmeasurable states, improving the reliability and accuracy of the system and proving the Lyapunov stability theory to be rigorously proven.
Li Tang, Ben Niu, Ning Zhao et al.
· International Journal of Rob... · 2 citations